VEMamba: Efficient Isotropic Reconstruction of Volume Electron Microscopy with Axial-Lateral Consistent Mamba

2026-02-28

AI Summary

This study addresses the challenge of anisotropic resolution in volume electron microscopy (VEM) imaging, where limited axial resolution hinders accurate three-dimensional structural analysis. To overcome this limitation, the authors propose VEMamba, a novel framework that achieves efficient isotropic reconstruction through 3D dependency reordering. The key innovations include an Axial-Lateral Chunk Selective Scanning Module (ALCSSM) to model directional consistency, a Dynamic Weight Aggregation Module (DWAM) for optimized feature fusion, and a self-supervised learning strategy combining realistic degradation modeling with Momentum Contrast (MoCo). Extensive experiments demonstrate that VEMamba significantly outperforms existing methods on both simulated and real-world anisotropic VEM data, achieving state-of-the-art performance in terms of reconstruction quality and computational efficiency.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search

Abstract

Volume Electron Microscopy (VEM) is crucial for 3D tissue imaging but often produces anisotropic data with poor axial resolution, hindering visualization and downstream analysis. Existing methods for isotropic reconstruction often suffer from neglecting abundant axial information and employing simple downsampling to simulate anisotropic data. To address these limitations, we propose VEMamba, an efficient framework for isotropic reconstruction. The core of VEMamba is a novel 3D Dependency Reordering paradigm, implemented via two key components: an Axial-Lateral Chunking Selective Scan Module (ALCSSM), which intelligently re-maps complex 3D spatial dependencies (both axial and lateral) into optimized 1D sequences for efficient Mamba-based modeling, explicitly enforcing axial-lateral consistency; and a Dynamic Weights Aggregation Module (DWAM) to adaptively aggregate these reordered sequence outputs for enhanced representational power. Furthermore, we introduce a realistic degradation simulation and then leverage Momentum Contrast (MoCo) to integrate this degradation-aware knowledge into the network for superior reconstruction. Extensive experiments on both simulated and real-world anisotropic VEM datasets demonstrate that VEMamba achieves highly competitive performance across various metrics while maintaining a lower computational footprint. The source code is available on GitHub: https://github.com/I2-Multimedia-Lab/VEMamba

Problem

• Volume Electron Microscopy
• anisotropic data
• axial resolution
• isotropic reconstruction

Innovation

• Mamba
• Isotropic Reconstruction
• Axial-Lateral Consistency
• 3D Dependency Reordering
• Volume Electron Microscopy